Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Steel
    -0.07
     tents
    -0.06
     steel
    -0.06
    .adj
    -0.06
     pipes
    -0.06
     Ton
    -0.06
     rpt
    -0.06
     Appointment
    -0.06
    аг
    -0.06
     chants
    -0.06
    POSITIVE LOGITS
     %}↵
    0.08
     denně
    0.07
     ')[
    0.07
    ンパ
    0.06
     ";↵
    0.06
     công
    0.06
    novation
    0.06
    helm
    0.06
     [(
    0.06
    는지
    0.06
    Act Density 0.232%

    No Known Activations